Triple

T16249406
Position Surface form Disambiguated ID Type / Status
Subject The Manxman E394459 entity
Predicate screenwriter P2831 FINISHED
Object Eliot Stannard E403836 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Eliot Stannard | Statement: [The Manxman, screenwriter, Eliot Stannard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Eliot Stannard
Context triple: [The Manxman, screenwriter, Eliot Stannard]
  • A. Eliot Stannard chosen
    Eliot Stannard was a British screenwriter best known for his extensive collaborations with Alfred Hitchcock during the silent film era.
  • B. Stewart Raffill
    Stewart Raffill is a British-born film director and screenwriter known for his work on science fiction and adventure films, including the cult movie "Mac and Me."
  • C. Eliot Spencer
    Eliot Spencer is a skilled martial artist and retrieval specialist who serves as the team's tough, soft-spoken hitter in the television series "Leverage."
  • D. Mark Stothert
    Mark Stothert is a music producer best known for his work with the artist Edie.
  • E. Philip Stapleton
    Philip Stapleton was a prominent Parliamentarian cavalry officer and politician during the English Civil War.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d87f2171208190951025e526947816 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e24594f23c8190bd59fcb2585cb5e3 completed April 17, 2026, 2:37 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00a5047a7c8190bac0ac9888547d16 completed May 10, 2026, 3:32 p.m.
Created at: April 10, 2026, 5:04 a.m.